Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already mark the tool as destructive and not read-only, but the description adds important context: the deletion is permanent, irreversible, and cascades to associated scoring data. This goes beyond the annotation flags and helps the agent warn users appropriately.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: the first states the action and key consequence, the second gives the prerequisite lookup step. Every sentence earns its place, with no redundant filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter destructive tool with annotations covering read-only/destructive/idempotent hints, the description is complete. It covers what is deleted, the irreversibility, the cascading data removal, and how to obtain the required ID.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one parameter, icpId, with 0% description coverage. The description tells the agent to find ICP IDs via campaignstack_list_icps, which provides practical sourcing guidance, but it does not clarify expected format, examples, or any nuance about the ID beyond its name.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('delete'), a clear resource ('an ICP'), and the extended scope ('its associated scoring data'). It clearly distinguishes this tool from related siblings like create_icp, update_icp, get_icp_scores, and list_icps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly directs the agent to use campaignstack_list_icps to find ICP IDs before deleting, which is a concrete prerequisite. It does not explicitly state when not to use this tool, but for a deletion operation the guidance is reasonably clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.